© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32574
    Prev
    Next
    INDEX
    Explanations

    time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ķ
    -0.10
    æĪijå½ĵæŶ
    -0.10
    çıįçıł
    -0.09
    å¾Ĺä½ı
    -0.09
    setItem
    -0.09
    ä¸įåıĬ
    -0.08
    管åĪ¶
    -0.08
    çİ°åľ¨çļĦ
    -0.08
    å½ĵäºĭ
    -0.08
    è¿Ļæīį
    -0.08
    POSITIVE LOGITS
     onwards
    0.09
    æĹ¢è¦ģ
    0.09
    пон
    0.09
    URN
    0.08
    å·±
    0.08
    åĽłä¸ºä»ĸ们
    0.08
    诱
    0.08
    oldt
    0.08
    ä¹ĭéĻħ
    0.08
    纵横
    0.08
    Activations Density 0.139%

    No Known Activations